Upload 5 files

Dockerfile

@@ -0,0 +1,22 @@
+# Use official python base image
+FROM python:3.10-slim
+
+# Install required system packages
+RUN apt-get update && apt-get install -y build-essential
+
+# Set working directory
+WORKDIR /code
+
+# Copy local files into container
+COPY requirements.txt .
+COPY main.py .
+COPY model.h5 .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Expose port
+EXPOSE 7860
+
+# Start the server
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

Usage.py

@@ -0,0 +1,21 @@
+import requests
+
+# Your deployed API URL
+api_url = "https://ali124k-124-HP-1.hf.space/predict"
+
+# Path to the image you want to classify
+image_path = "Apple_scab.jpg"   # <-- replace this with your image path
+
+# Open image file in binary mode
+with open(image_path, "rb") as image_file:
+    files = {"file": image_file}
+    response = requests.post(api_url, files=files)
+
+# Check response status
+if response.status_code == 200:
+    result = response.json()
+    print("Prediction:", result["prediction"])
+    print("Confidence:", result["confidence"])
+else:
+    print("Error:", response.status_code)
+    print(response.text)

main.py

@@ -0,0 +1,33 @@
+from fastapi import FastAPI, UploadFile, File
+import numpy as np
+from PIL import Image
+import io
+from tensorflow import keras
+
+# Load model
+model = keras.models.load_model('model.h5')
+
+# Class labels (ordered list)
+class_labels = [
+    'COVID19', 'NORMAL', 'PNEUMONIA' 
+]
+
+# Initialize FastAPI app
+app = FastAPI()
+
+# Preprocess function
+def preprocess_image(image_bytes):
+    image = Image.open(io.BytesIO(image_bytes)).convert('RGB')
+    image = image.resize((224, 224))
+    img_array = np.array(image) / 255.0  # normalize (assuming your model was trained with normalization)
+    img_array = np.expand_dims(img_array, axis=0)  # add batch dimension
+    return img_array
+
+@app.post("/predict")
+async def predict(file: UploadFile = File(...)):
+    image_bytes = await file.read()
+    img_array = preprocess_image(image_bytes)
+    predictions = model.predict(img_array)
+    predicted_class = class_labels[np.argmax(predictions)]
+    confidence = float(np.max(predictions))
+    return {"prediction": predicted_class, "confidence": confidence}

model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50773612987f3a24633d93ea7e7cff08480b0ddd23e0ea07a623b4803726e279
+size 136038112

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+pillow
+tensorflow
+python-multipart
+numpy